Borrowing it
Nothing to install: this file belongs to xun404/dsh-pihuo-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xun404/dsh-pihuo-plugins/main/.agents/skills/dsh-plugin-review/SKILL.mdgit clone --depth 1 https://github.com/xun404/dsh-pihuo-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-review)<a href="https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-review"><img src="https://agentmods.dev/badge/skills/xun404/dsh-pihuo-plugins/dsh-plugin-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-review"><img src="https://agentmods.dev/badge/skills/xun404/dsh-pihuo-plugins/dsh-plugin-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.01031 |
| Opus 5 | $0.00038 | $0.00515 |
| Sonnet 5 | $0.00015 | $0.00206 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
dsh-plugin-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
审查 dsh 插件
只报告违反本仓库技能的问题。规则正文在对应技能,这里不下第二份定义。先读改动与插件根目录的 package.json、cordis.patch.yml、入口模块。
对照源码:../deepseek-harness(若存在)。
流程
- 判定形态:工具 / 服务 / 适配器 / 钩子 / Client / 纯 bundle。选错形态本身就是 finding。
- 按下面清单逐项核对,每条 finding 写:位置、违反的规则(链到技能)、怎么改。
- 区分错误(必须改)与建议(规范倾向)。
- 不要评审 harness 第一方风格差异(i18n yaml、invariant 文件等),除非树外包也声明要跟第一方门禁。
清单
形态与归属 — conventions
- 新行为挂在已有扩展点,没有改 agent loop / 没有旁路喂模型。
- 模型可见输入能从会话日志重建。
- 该拆 seam 时 Provider 与 Consumer 不互相依赖。
- 包名、ctx key、工具名、事件名符合命名表。
- 没有把产品功能做成
cordis_define动态包。 - 导出符号与非显然边界有准确 JSDoc;没有过时或复述式注释(comments)。
运行时 — runtime
- 入口是函数 /
{ apply }/Service之一;有name。 -
inject覆盖apply里读的必需服务;可选的用ctx.get。 - 无模块顶层副作用。
- 外部资源在
ctx.effect;有序清理在同一个 disposer。 - Waterfall 观察者调用
next();政策插件的短路是故意的。 -
Config是 Schemastery(Standard Schema),不是普通对象。 - 可调超时/路径/开关在 Config 里,能在 patch 改掉。
工具(若有)— templates
-
defineTool:规范值 +output.render;execute尊重exec.signal。 - 政策不在
execute里。 -
presentCall/presentResult若存在则是纯函数。
组装 — compose
- 有
dsh.bundle.patch,且 patch 在files里。 - patch
id稳定;name是包名(不是作者机器路径)。 - 覆盖已有行时重述完整
config。 - cordis 与所用 Definition 在
peerDependencies。 - TypeScript 包有自包含
prepare,或只发预构建产物。
浏览器半(若有)— client
- 声明
dsh.client+exports["./client"],且 Host 行会挂上该包。 -
./client是__ModuleLoader__.loadCJS factory,id 等于包名;reactexternal。 - 只通过
slots.register组合;组件不碰ctx。 -
./client没有多余值导出,没有跨插件 import 组件。 - 没有假设自己会出现在内置设置白名单里。
输出格式
## 结论
<一句话:可以合并 / 先改错误>
## 错误
- `path:line` — <规则链接> — <改法>
## 建议
- ...
## 已核对且通过
- <短列表>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 83 lines · 76 tokens per session scan A 50d689e0910d
dsh-plugin-review is a skill published in the GitHub repository xun404/dsh-pihuo-plugins (2 stars, last pushed 23d ago), licensed MIT. It adds 76 tokens to every session and 1,031 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
code-review-cn
A Chinese-language guide for reviewing code changes, pull requests, and diffs. It prioritizes correctness, resource cleanup, security, matching documentation, and tests before style.
pr-description
A writing guide for pull request descriptions. A pull request is a proposed set of code changes for review and merging.
refactor-safely
A safe code-refactoring guide for changing code structure while keeping its external behavior the same. Refactoring means reorganizing code without changing what it does.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
review-changes
Review local code changes for concrete correctness, regression, security, and test gaps before shipping.
codex-sync
Operate dsh-codex-sync from this session — preview and import Codex chats, toggle Skills/MCP/import settings, check MCP mirror health, install the reverse MCP bridge.